Multi-Agent Collaborative Framework for Intelligent IT Operations

This paper proposes AOI, a novel multi-agent framework that integrates specialized agents and an LLM-based Context Compressor to address the challenges of modern cloud-native IT infrastructures.

Details

The proliferation of cloud-native architectures has led to exceedingly complex and volatile IT infrastructures, generating overwhelming volumes of operational data. This complexity causes critical bottlenecks in conventional systems, such as inefficient information processing, poor task coordination, and loss of contextual continuity during fault diagnosis and remediation. To address these challenges, the authors propose AOI (AI-Oriented Operations), a novel multi-agent collaborative framework that integrates three specialized agents with an LLM-based Context Compressor. The key innovations include a dynamic task scheduling strategy that adaptively prioritizes operations based on real-time system states, and a three-layer memory architecture comprising Working, Episodic, and Semantic layers that optimizes context retention and retrieval. Extensive experiments on both synthetic and real-world benchmarks demonstrate that AOI effectively mitigates information overload, achieving a 72.4% context compression ratio while preserving 92.8% of critical information, and significantly enhances operational efficiency, attaining a 94.2% task success rate and reducing the Mean Time to Repair (MTTR) by 34.4% compared to the best baseline.